Speech Dereverberation On Whamr
評価指標
ESTOI
PESQ
SI-SDR
SI-SDRi
SRMR
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | ESTOI | PESQ | SI-SDR | SI-SDRi | SRMR | Paper Title | Repository |
|---|---|---|---|---|---|---|---|
| Conv-TasNet DAE | 93 | 3.46 | 12.03 | 7.63 | 8.7 | Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation | |
| Non-Real-Time MultiScale+ | - | 3.16 | 10.4 | - | - | Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net | |
| WD-TCN | 93.5 | 3.5 | 12.26 | - | 8.8 | Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation | - |
0 of 3 row(s) selected.